INDEX
Explanations
information related to a specific location or setting, focusing on descriptions of physical attributes and historical background
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1150
+0.12
0.4%
1177
+0.11
0.3%
776
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1585
+0.12
0.02
1729
+0.11
0.06
581
+0.08
0.04
Negative Logits
ordina
-1.17
wien
-1.17
milano
-1.17
kombi
-1.16
utop
-1.13
bayern
-1.12
frankfurt
-1.11
incess
-1.11
hek
-1.10
banan
-1.09
POSITIVE LOGITS
original
0.67
preserved
0.67
original
0.60
donated
0.59
recovered
0.58
museum
0.56
restored
0.55
memorabilia
0.55
Original
0.55
originals
0.55
Activations Density 0.559%